Automation and Sociophonetics

Josef Fruehwald

October 23, 2014

Introduction

Outline of the talk

  • The Benefits of Automation
  • The Real Benefits of Automation
  • How FAVE works
  • The FUD Surrounding Automation

The Benefits of Automation

Some Undeniable Benefits

  • It’s a bit faster.
  • You get more, and richer data.

Dinkin (2009)

  • 57,464 formant measurements
  • 119 speakers
  • Average of 483 mesurements per speaker

Philadelphia Neighborhood Corpus

  • 743,802 formant measurements
  • 397 speakers
  • Average of 1,874 measurements per speaker
  • Average of 0.94 vowels per second.

More Data

/ay/ followed by different /t,d/ contexts.

faithful phrase_flap word_flap
D 1,190 384 245
T 4,024 524 285

More Data

plot of chunk unnamed-chunk-7

More Data

plot of chunk unnamed-chunk-9

Richer Data

transcription

Richer Data

alignment

Richer Data

plot of chunk unnamed-chunk-11

Richer Data

plot of chunk unnamed-chunk-12

The Real Benefits of Automation

Reproducibility

plot of chunk unnamed-chunk-15

Reproducibility

Reproducibility is Comparability

Researcher Heuristics

  • Choosing a measurement point.
  • Adjusting the LPC settings.
  • Choosing vowels to measure or ignore.
  • etc

Researcher Effects

  • How explicitly defined their heuristics are.
  • How strictly they enforce them.
  • How experienced and skilled they are.
  • Their recent caffiene consumption, and quality of previous night’s sleep.

Automation

Knowable, Explicitly Defined, Exceptionless

  • Measurement point selection method.
  • LPC parameter setting method.
  • Decision process for measuring a vowel or not.

Automation

s1_t1

s2_t1

s2_t1

Automation

s1_t1

s2_t1

Automation

Eliminated

  • Researcher experience and skill.
  • …oops

Publication

github

Reproducibility

Reproducibility

formantlog

FAVE

The FAVE Toolkit

  • FAVE-align
    • provides forced alignment
  • FAVE-extract
    • automated formant analysis

FAVE Design Features & Bugs

  • Focus on formants.
  • Focus on point measurements.
  • Tries to emulate how humans have done formant analysis.

FAVE

library(shiny)
shinyAppDir("formants/")

FAVE

  • For each vowel token, the F1 and F2 estimates you could get for different LPC parameter settings constitute a candidate set.
  • Choose a winner based on its multivariate distance (based on F1, F2, log(B1), log(B2)) to the Atlas of North American English’s distribution for that vowel class.
  • Logic: If there is an LPC setting whch is produces a measurement close to the ANAE distribution for that vowel class, it’s probably ok.

FAVE - Once more, but Bayesian this time

  • The ANAE distribution for a vowel class is the prior.
  • The candidate set of potential formant estimates is the likelihood.
  • The winner is the posterior.


  • Like most worries about Bayesian reasoning, people worry that the prior might exert too strong an influence on the posterior.
  • Fortunately, the prior’s influence here doesn’t seem to be too strong.

FAVE - Step 1

library(shiny)
shinyAppDir("fave/")

FAVE - Remeasurement

library(shiny)
shinyAppDir("remeasure/")

FAVE - Step 2

library(shiny)
shinyAppDir("fave2/")

FAVE - Results

library(shiny)
shinyAppDir("fave_results/")

FAVE - Future Directions

  • feature/iterremeasure
    • Continue iterating through re-estimation either until it arrives at a stable distribution, or a maximum iteration is reached.
  • feature/bootstrap
    • Try to figure out the best LPC setting based on the distribution of the candidate set alone.
    • This approach would only be appropriate for vowel classes with a lot of tokens.

FAVE - Future Directions

plot of chunk unnamed-chunk-22

Future Directions

  • Customizable measurement point heuristics
  • Customizable vowel system configurations

Future Directions

Other approaches to vowel measurement might try:

  • MFCCs + Multidimensional scaling of some sort.
  • Treating formants more like a probability distribution
    FAVE will stick to automating “traditional” approaches.

Fear, Uncertainty, Doubt

Errors

People make errors too

errors

“Black Box”

People are black boxes

ppl

FAVE is not a black box

github

It’s like…

ppl

It’ll encourage…

Choloepus didactylus - Buffalo Zoo” by Dave Pape - Own work. Licensed under Public domain via Wikimedia Commons.

Moral Panic

  • Either we’re clever enough to learn how to appropriately use new research tools, or we’re not.
  • Automation is not an excuse to understand your data less well.


  • The proof is in the pudding.